Spaces:

---

Duplicated from  zerogpu-aoti/wan2-2-fp8da-aoti-faster

r3gm

/

wan2-2-fp8da-aoti-preview

like 2.29k

Running on Zero

I would like to know what hardware you need to run this locally. I tried to run it with an Nvidia RTX3090 (24GB) with NVIDIA Container Toolkit and ran in an Out-Of-Memory issue. Did anyone got it running locally and which GPU do you have?

How i set it up:

1. Update Ubuntu:
   sudo apt update && sudo apt upgrade -y

2. Install NVIDIA Drivers:
   ubuntu-drivers devices
   sudo apt install nvidia-driver-XXX # Replace XXX with recommended version
   sudo reboot

3. Install Docker and NVIDIA Container Toolkit:
   sudo apt install apt-transport-https ca-certificates curl software-properties-common -y
   curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
   sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
   sudo apt update
   sudo apt install docker-ce -y

sudo usermod -aG docker $USER
newgrp docker

distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt update
sudo apt install -y nvidia-docker2
sudo systemctl restart docker

4. Test GPU support:
   docker run --rm --gpus all nvidia/cuda:13.1.1-cudnn-devel-ubuntu24.04 nvidia-smi

5. Run Space:
   docker run -it -p 7860:7860 --platform=linux/amd64 --gpus all
   registry.hf.space/r3gm-wan2-2-fp8da-aoti-preview:latest python app.py